paper-with-me

홈 › Papers

Open-Domain Contextual Link Prediction and its Complementarity with Entailment Graphs

2021-11-01 · Findings (EMNLP) 2021 11 · Mohammad Javad Hosseini, Shay B. Cohen, Mark Johnson, Mark Steedman

An open-domain knowledge graph (KG) has entities as nodes and natural language relations as edges, and is constructed by extracting (subject, relation, object) triples from text. The task of open-domain link prediction is to infer missing relations in the KG. Previous work has used standard link prediction for the task. Since triples are extracted from text, we can ground them in the larger textual context in which they were originally found. However, standard link prediction methods only rely on the KG structure and ignore the textual context that each triple was extracted from. In this paper, we introduce the new task of open-domain contextual link prediction which has access to both the textual context and the KG structure to perform link prediction. We build a dataset for the task and propose a model for it. Our experiments show that context is crucial in predicting missing relations. We also demonstrate the utility of contextual link prediction in discovering context-independent entailments between relations, in the form of entailment graphs (EG), in which the nodes are the relations. The reverse holds too: context-independent EGs assist in predicting relations in context.

📄 PDF Abstract BibTeX

Code (1)

mjhosseini/open_contextual_link_pred 공식 구현 pytorch

Tasks

Link PredictionPrediction

Similar Papers 제목 키워드 기반

Zepyros: A webserver to evaluate the shape complementarity of protein-protein interfaces

2024-02-10 · Mattia Miotto, Lorenzo Di Rienzo, Leonardo Bo', Giancarlo Ruocco 외

Shape complementarity of molecular surfaces at the interfaces is a well-known characteristic of protein-protein binding regions, and it is critical in influencing the stability of the complex. Measuring such complementar…

IMF: Interactive Multimodal Fusion Model for Link Prediction

2023-03-20 · Xinhang Li, Xiangyu Zhao, Jiaxing Xu, Yong Zhang 외

Link prediction aims to identify potential missing triples in knowledge graphs. To get better results, some recent studies have introduced multimodal information to link prediction. However, these methods utilize multimo…

Contrastive LearningKnowledge GraphsLink PredictionPrediction

OKGIT: Open Knowledge Graph Link Prediction with Implicit Types

2021-06-24 · Chandrahas, Partha Pratim Talukdar

Open Knowledge Graphs (OpenKG) refer to a set of (head noun phrase, relation phrase, tail noun phrase) triples such as (tesla, return to, new york) extracted from a corpus using OpenIE tools. While OpenKGs are easy to bo…

Knowledge GraphsLink PredictionPredictionQuestion Answering+2

Toward Human-AI Complementarity Across Diverse Tasks

2026-04-13 · Yuzheng Xu, Annya Dahmani, Matthew D. Blanchard, Niclas Dern 외 arxiv

Human-AI complementarity, the idea that combining human and AI judgments can outperform either alone, offers a promising pathway toward robust oversight of advanced AI systems. However, whether human-AI complementarity c…

ReInform: Selecting paths with reinforcement learning for contextualized link prediction

2022-11-19 · Marina Speranskaya, Sameh Methias, Benjamin Roth

We propose to use reinforcement learning to inform transformer-based contextualized link prediction models by providing paths that are most useful for predicting the correct answer. This is in contrast to previous approa…

Link PredictionPredictionreinforcement-learningReinforcement Learning+1